{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1805.10123","title":"TADAM: Task dependent adaptive metric for improved few-shot learning","created":"2018-05-23","cited_by_count":408},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2103.10158","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","created":"2021-03-18","cited_by_count":227},{"id":"1906.07697","title":"Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes","created":"2019-06-18","cited_by_count":131},{"id":"1702.05538","title":"Dataset Augmentation in Feature Space","created":"2017-02-17","cited_by_count":124},{"id":"2112.13492","title":"Vision Transformer for Small-Size Datasets","created":"2021-12-27","cited_by_count":122},{"id":"1912.03432","title":"Improved Few-Shot Visual Classification","created":"2019-12-07","cited_by_count":115},{"id":"2106.03746","title":"Efficient Training of Visual Transformers with Small Datasets","created":"2021-06-07","cited_by_count":108},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"1612.04426","title":"Improving Neural Language Models with a Continuous Cache","created":"2016-12-13","cited_by_count":82},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81},{"id":"2003.04151","title":"Embedding Propagation: Smoother Manifold for Few-Shot Classification","created":"2020-03-09","cited_by_count":80},{"id":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","cited_by_count":57},{"id":"1902.03477","title":"The Omniglot challenge: a 3-year progress report","created":"2019-02-09","cited_by_count":54},{"id":"1910.04176","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","created":"2019-10-09","cited_by_count":45},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35},{"id":"2208.07220","title":"PatchDropout: Economizing Vision Transformers Using Patch Dropout","created":"2022-08-10","cited_by_count":28},{"id":"1805.08709","title":"A Simple Cache Model for Image Recognition","created":"2018-05-21","cited_by_count":20},{"id":"2204.00484","title":"Proper Reuse of Image Classification Features Improves Object Detection","created":"2022-04-01","cited_by_count":20},{"id":"2212.14453","title":"Learning Multimodal Data Augmentation in Feature Space","created":"2022-12-29","cited_by_count":18},{"id":"2305.16999","title":"Three Towers: Flexible Contrastive Learning with Pretrained Image Models","created":"2023-05-26","cited_by_count":11}],"next_cursor":null}